gpt-oss-120b-MLX-bf16
Summary. This is a non-quantized MLX conversion of gpt-oss-120B in bfloat16 (bf16). Built for Apple Silicon with Metal...
Метка: arm64
gpt-oss-20b-MLX-4bit-gs32
Summary. This is a 4-bit (Q4) MLX quantization of gpt-oss-20B (sparse Mixture-of-Experts, MPx4). Group size is 32. Built...
gemma-4-31B-it-speculator.eagle3-NVFP4
Квантование NVFP4 RedHatAI/gemma-4-31B-it-speculator.eagle3 — официальный разработчик RedHat/Neural Magic EAGLE-3 для Gemma 4 31B (dense). Встроенная замена для чертежника...
vllm-dgx-spark-gb10
Ключевые слова: vLLM DGX Spark, NVIDIA GB10, Blackwell GPU, SM121, ARM64 LLM, CUDA 13.1, запуск докера вывода Qwen3...